...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Selected Topics in Signal Processing, IEEE Journal of >Inverted Alignments for End-to-End Automatic Speech Recognition
【24h】

Inverted Alignments for End-to-End Automatic Speech Recognition

机译：端到端自动语音识别的反向对齐

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper, we propose an inverted alignment approach for sequence classification systems like automatic speech recognition (ASR) that naturally incorporates discriminative, artificial-neural-network-based label distributions. Instead of aligning each input frame to a state label as in the standard hidden Markov model (HMM) derivation, we propose to inversely align each element of an HMM state label sequence to a segment-wise encoding of several consecutive input frames. This enables an integrated discriminative model that can be trained end-to-end from scratch or starting from an existing alignment path. The approach does not assume the usual decomposition into a separate (generative) acoustic model and a language model, and allows for a variety of model assumptions, including statistical variants of attention. Following our initial paper with proof-of-concept experiments on handwriting recognition, the focus of this paper was the investigation of integrated training and an inverted decoding approach, whereas the acoustic modeling still remains largely similar to standard hybrid modeling. We provide experiments on the CHiME-4 noisy ASR task. Our results show that we can reach competitive results with inverted alignment and decoding strategies.
机译：在本文中，我们为诸如自动语音识别（ASR）之类的序列分类系统提出了一种反向比对方法，该方法自然地结合了基于人工神经网络的区分性标签分布。与其像标准隐式马尔可夫模型（HMM）推导中那样，将每个输入帧与状态标签对齐，不如将HMM状态标签序列的每个元素与多个连续输入帧的分段编码反向对齐。这实现了集成的判别模型，该模型可以从头开始或从现有的对齐路径开始进行端到端训练。该方法没有假定通常分解为单独的（生成的）声学模型和语言模型，而是允许使用各种模型假设，包括关注度的统计变体。继我们的初步论文以笔迹识别的概念验证实验为基础之后，本文的重点是对综合训练和反向解码方法的研究，而声学建模仍在很大程度上类似于标准混合建模。我们提供有关CHiME-4嘈杂ASR任务的实验。我们的结果表明，我们可以通过反向对齐和解码策略获得竞争性结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号